CN110414315A - A kind of collaboration supervision method of isomery security system - Google Patents
A kind of collaboration supervision method of isomery security system Download PDFInfo
- Publication number
- CN110414315A CN110414315A CN201910502389.2A CN201910502389A CN110414315A CN 110414315 A CN110414315 A CN 110414315A CN 201910502389 A CN201910502389 A CN 201910502389A CN 110414315 A CN110414315 A CN 110414315A
- Authority
- CN
- China
- Prior art keywords
- security system
- eigenvalue
- facial image
- supervision method
- collaboration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Abstract
The present invention relates to field of security technologies, and in particular to a kind of collaboration supervision method of isomery security system.The isomery security system includes the first security system and the second security system, first security system is equipped with the list library of deploying to ensure effective monitoring and control of illegal activities for storing multiple first facial images, second security system acquires the second facial image, the collaboration supervision method extracts the First Eigenvalue of the first facial image and the Second Eigenvalue of the second facial image comprising steps of by identical human face recognition model；Similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue, obtains the similarity of the two；If similarity is higher than preset value, it is believed that corresponding the first facial image and the second facial image is same people.Transmiting contrast is carried out by the characteristic value of image between two security systems, avoids being transmitted using video flowing or facial image stream, reduces the load pressure of security system, meanwhile, avoid clue from omitting, reduction, which is deployed to ensure effective monitoring and control of illegal activities, assesses difficulty, and data transmission efficiency is high.
Description
Technical field
The present invention relates to field of security technologies, and in particular to a kind of collaboration supervision method of isomery security system.
Background technique
Current manual's intellectual development, recognition of face or other biological feature or behavioural characteristic identification technology are widely applied
In security system.For example face is deployed to ensure effective monitoring and control of illegal activities, and analyzes the face in video flowing in real time, discovery blacklist suspect just alerts.
The principle of recognition of face is input facial image, extracts face characteristic by human face recognition model calculating, subsequent
The same person is determined whether by comparing face characteristic.But the human face recognition model of different company is different, identical face figure
Different faces identification model version difference as different feature or even same company can be generated under different identification models,
Feature is also different.So face characteristic can not be used in heterogeneous system, it can only Transfer Standards image between heterogeneous system.
It, can only be level of confidentiality meanwhile between different security level system, such as public security security system and real estate garden security system
Lower video flowing or image stream imported into the higher system of level of confidentiality.But the often lower system of level of confidentiality, camera is more
More, magnitude is several times as much as the higher system of level of confidentiality.If video flowing or image stream all from the lower system introducing of level of confidentiality to level of confidentiality compared with
High system can not be handled then being a huge load pressure to the higher system of level of confidentiality.So hot system
The more important camera of individual assessments or video flowing access can only be selected, thus brings to deploy to ensure effective monitoring and control of illegal activities and assesses difficulty, also omit
A large amount of clues.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the above drawbacks of the prior art, providing a kind of isomery security protection system
The collaboration supervision method of system overcomes between existing different security system, video flowing between the security system of different security level or
Image stream cannot import completely, be easy to cause the omission of clue, deploy to ensure effective monitoring and control of illegal activities and assess the big problem of difficulty.
The technical solution adopted by the present invention to solve the technical problems is: the collaboration for providing a kind of isomery security system is deployed to ensure effective monitoring and control of illegal activities
Method, the isomery security system include the first security system and the second security system, and first security system is equipped with storage
The list library of deploying to ensure effective monitoring and control of illegal activities of multiple first facial images, second security system acquire the second facial image, the collaboration cloth prosecutor
Method comprising steps of
By identical human face recognition model, extract the first facial image the First Eigenvalue and the second facial image second
Characteristic value；
Similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue, obtains the similarity of the two；
If similarity is higher than preset value, it is believed that corresponding the first facial image and the second facial image is same people.
Still more preferably scheme of the invention is: the collaboration supervision method further comprises the steps of:
After extracting the Second Eigenvalue of the First Eigenvalue and the second facial image of the first facial image, by fisrt feature
Value and Second Eigenvalue are transmitted to a processing module；
Similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue in the processing module.
Still more preferably scheme of the invention is: the collaboration supervision method further comprises the steps of:
If similarity is higher than preset value, warning information of deploying to ensure effective monitoring and control of illegal activities is generated；
The processing module warning information that will deploy to ensure effective monitoring and control of illegal activities is transmitted to the first security system.
Still more preferably scheme of the invention is: edge calculations server is arranged in the second security system, in edge meter
Calculate the processing module that server disposition is used to carry out the First Eigenvalue and Second Eigenvalue similarity comparison calculating.
Still more preferably scheme of the invention is: first security system is passed the First Eigenvalue by encrypted tunnel
Transport to processing module.
Still more preferably scheme of the invention is: the encrypted tunnel uses RSA Algorithm.
Still more preferably scheme of the invention is: edge calculations server is arranged in the first security system, in edge meter
Calculate the processing module that server disposition is used to carry out the First Eigenvalue and Second Eigenvalue similarity comparison calculating.
Still more preferably scheme of the invention is: regularly updating the list library of deploying to ensure effective monitoring and control of illegal activities of the first security system.
Still more preferably scheme of the invention is: the list library of deploying to ensure effective monitoring and control of illegal activities includes personnel's name, the first facial image, year
The information such as age, gender.
Still more preferably scheme of the invention is: the level of confidentiality of first security system is higher than the second security system.
The beneficial effects of the present invention are compared with prior art, by using identical human face recognition model, extract the
In one security system in the First Eigenvalue of the first facial image and the second security system the second facial image Second Eigenvalue,
Then similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue, the similarity of the two is obtained, if similarity is higher than
Preset value, it is believed that corresponding the first facial image and the second facial image is same people, the first security system and the second security protection
Transmiting contrast is carried out by the characteristic value of image between system, video flowing or facial image stream is avoided to carry out in different security systems
Transmission, reduces the load pressure of security system, while clue being avoided to omit, and reduction, which is deployed to ensure effective monitoring and control of illegal activities, assesses difficulty, and improves different security protections
The efficiency of transmission of data among systems.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the flow diagram of the collaboration supervision method of isomery security system of the invention；
Fig. 2 is the idiographic flow block diagram of the collaboration supervision method of isomery security system of the invention.
Specific embodiment
Now in conjunction with attached drawing, elaborate to presently preferred embodiments of the present invention.
Embodiment one
As shown in Figure 1, the present invention provides a kind of preferred embodiment of the collaboration supervision method of isomery security system.
The isomery security system includes the first security system and the second security system, and first security system is equipped with and deposits
The list library of deploying to ensure effective monitoring and control of illegal activities of multiple first facial images is stored up, second security system acquires the second facial image.The isomery security protection
The collaboration supervision method of system comprising steps of
S10, by identical human face recognition model, extract the First Eigenvalue and the second facial image of the first facial image
Second Eigenvalue；
S20, similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue, obtains the similarity of the two；
If S30, similarity are higher than preset value, it is believed that corresponding the first facial image and the second facial image is same
People.
The first face extracted between first security system and the second security system by using identical human face recognition model
The Second Eigenvalue of the First Eigenvalue of image and the second facial image carrys out transmiting contrast calculating, judges the first facial image and the
Whether two facial images are same people, if similarity is higher than preset value, then it is assumed that corresponding the first facial image and the second people
Face image is same people.Transmiting contrast is carried out by the characteristic value of image between first security system and the second security system, is kept away
Exempt from video flowing or facial image stream to be transmitted in different security systems, reduces the load pressure of security system, while avoiding line
Rope is omitted, and reduction, which is deployed to ensure effective monitoring and control of illegal activities, assesses difficulty, and improves the efficiency of transmission of data between different security systems；And directly use the
One characteristic value and Second Eigenvalue are compared, and substantially increase the real-time and efficiency of face alignment.
Isomery is a kind of characteristic comprising heterogeneity.Heterogeneous system refers to different two systems, isomery in the present invention
System includes different the first security system and the second security system.
Wherein, human face recognition model can be and be deployed to ensure effective monitoring and control of illegal activities first in list library using obtaining for identification in the first security system
The human face recognition model of face characteristic in facial image can also use in the second security system and obtain the second face for identification
The human face recognition model of face characteristic in image.The fisrt feature of the first facial image is extracted using identical human face recognition model
The Second Eigenvalue of value and the second facial image, the First Eigenvalue and Second Eigenvalue comparing result have more referential, accuracy rate
It is higher.
And the collaboration supervision method of the isomery security system be applied to the first security system and the second security system it
Between collaboration deploy to ensure effective monitoring and control of illegal activities, the first security system and the second security system can be the security system of identical level of confidentiality, be also possible to difference
The security system of level of confidentiality.The transmission for the characteristic value extracted from the facial image of two security systems will not be by the level of confidentiality of security system
The influence of height, the low security system camera of level of confidentiality is more, and magnitude is several times as much as the higher system of level of confidentiality, the facial image obtained
Still extractable characteristic value, the characteristic value with data volume much smaller than facial image are transmitted to hot security system, avoid clue
Omission, meanwhile, promoted efficiency of transmission, improve the real-time of face alignment.Collaboration supervision method of the invention is preferably applied to
Collaboration between the different security system of two levels of confidentiality is deployed to ensure effective monitoring and control of illegal activities.
In the present embodiment, the level of confidentiality of first security system is higher than the second security system.If using the first security system
Human face recognition model, then can be by issuing human face recognition model to the second security system, in the second security system using issuing
Human face recognition model extract the Second Eigenvalue of acquired second facial image；If using the recognition of face of the second security system
Model then can allow the second security system to upload human face recognition model to open platform, open flat by providing an open platform
Platform dispatches the human face recognition model of the second security system, and using the first facial image in list library of deploying to ensure effective monitoring and control of illegal activities as input, obtains
The First Eigenvalue corresponding to human face recognition model.
Further, after step S10, the collaboration supervision method is further comprised the steps of:
S21, the First Eigenvalue and Second Eigenvalue are transmitted to a processing module；
S22, similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue in the processing module.
Specifically, in the first security system, using human face recognition model, using AI deep learning algorithm, extraction is deployed to ensure effective monitoring and control of illegal activities
The key message of face in the first facial image of list library, that is, the First Eigenvalue of the first facial image in list library of deploying to ensure effective monitoring and control of illegal activities, such as
The profile of face, the attribute informations such as eyes, nose, mouth, combination form a first eigenvector；In the second security system
In, using same human face recognition model, using AI deep learning algorithm, extract the pass of face in the second acquired facial image
Key information obtains the Second Eigenvalue in the second facial image, such as the profile of face, the attributes such as eyes, nose, mouth letter
Breath, combination form a second feature vector.By calculating the corresponding first eigenvector and second being combined into of the First Eigenvalue
The similarity of the corresponding second feature vector being combined into of characteristic value, similarity is compared with preset value, if similarity is more than
Preset value, it is believed that corresponding the first facial image and the second facial image is same people.
And the First Eigenvalue is extracted to the first facial image in list library of deploying to ensure effective monitoring and control of illegal activities in the first security system, in the first peace
Anti- system extracts Second Eigenvalue to the second facial image of acquisition, has lacked the to the second facial image in the first security system
The extraction of two characteristic values handles mould alternatively, having lacked the extraction of the First Eigenvalue to the first facial image in the second security system
Block directly compares calculating using the First Eigenvalue and Second Eigenvalue, saves the calculation amount of half, improves face alignment
Real-time.
Further, after step S30, the collaboration supervision method is further comprised the steps of:
If S40, similarity are higher than preset value, warning information of deploying to ensure effective monitoring and control of illegal activities is generated；
S50, the processing module warning information that will deploy to ensure effective monitoring and control of illegal activities are transmitted to the first security system.
The Second Eigenvalue extracted in the second facial image obtained in second security system is deployed to ensure effective monitoring and control of illegal activities with the first security system
The similarity of the First Eigenvalue extracted in the second facial image in list library is more than preset value, illustrates that the second security system obtains
Personnel's hit of the second facial image deploy to ensure effective monitoring and control of illegal activities list library, processing module generation, which is deployed to ensure effective monitoring and control of illegal activities, alerts this information, and the alarm letter that will deploy to ensure effective monitoring and control of illegal activities
Breath is transmitted to the first security system, is convenient for subsequent security protection measure.
In the present embodiment, edge calculations server is set in the second security system, is used in edge calculations server disposition
The processing module of similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue.
Processing module obtains the First Eigenvalue and the second security protection of the first security system transmission by edge calculations server
The Second Eigenvalue of system transmission, and the similarity of the two is calculated, second that the second security system obtains is judged by similarity
In the list library of deploying to ensure effective monitoring and control of illegal activities of facial image face and the first security system in the first facial image face similarity, similarity gets over
Height, the probability that two facial images of expression correspond to the same person are bigger；When similarity is more than preset value, alarm signal of deploying to ensure effective monitoring and control of illegal activities is generated
Breath, and pass through edge calculations server transport to the first security system.
Wherein it is possible to which processing module is deployed on any edge calculations server for needing to dispose.
Further, the First Eigenvalue is transmitted to processing module by encrypted tunnel by first security system.
Wherein, the encrypted tunnel uses RSA Algorithm.
RSA Algorithm is a kind of rivest, shamir, adelman, is a kind of algorithm of cryptography, it needs two keys, and one is
Public-key cryptography, the other is private cipher key, one when be used as encryption, another is then used as decryption.RSA Algorithm is first
It can be used for the algorithm of encrypted and digitally signed simultaneously, be also easy to understand and operate.RSA public-key encryptosystem, so-called public affairs
Opening secret key cipher system is exactly using different encryption key and decruption key, is a kind of " solved out by known encryption key derivation
Key is computationally infeasible " cipher system.
Processing module is transmitted using RSA Algorithm between the first security system and processing module by edge calculations server
Data encrypted, reduction artificially interfere the risk deployed to ensure effective monitoring and control of illegal activities.
In the present embodiment, during entire collaboration is deployed to ensure effective monitoring and control of illegal activities, the list library of deploying to ensure effective monitoring and control of illegal activities of the first security system can be regularly updated.
In the first security system, list library of deploying to ensure effective monitoring and control of illegal activities periodically is updated list library of deploying to ensure effective monitoring and control of illegal activities with certain timeliness,
Accordingly, the corresponding the First Eigenvalue of the first facial image extracted by human face recognition model is also with the update in list library of deploying to ensure effective monitoring and control of illegal activities
And update, guarantee the efficiency and accuracy that security protection is deployed to ensure effective monitoring and control of illegal activities.
In the present embodiment, the list library of deploying to ensure effective monitoring and control of illegal activities includes the information such as personnel's name, the first facial image, age, gender.
Embodiment two
The present embodiment and embodiment one the difference is that, in the present embodiment, edge meter is set in the first security system
Server is calculated, is used to carry out similarity comparison calculating to the First Eigenvalue and Second Eigenvalue in edge calculations server disposition
Processing module.
In the present embodiment, extracted in the second facial image that the second security system need to only be obtained through human face recognition model
Second Eigenvalue be transmitted to be set to and be deployed in the processing module of the first security system, also, Second Eigenvalue is in the first security protection
It is transmitted between system and the second security system by encrypted tunnel, whether the second security system is not aware that and specifically triggers
It deploys to ensure effective monitoring and control of illegal activities alarm, reduces human intervention and alarm the risk reported.
It should be understood that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations, to ability
It for field technique personnel, can modify to technical solution illustrated in the above embodiments, or special to part of technology
Sign is equivalently replaced；And all such modifications and replacement, it should all belong to the protection domain of appended claims of the present invention.
Claims (10)
1. a kind of collaboration supervision method of isomery security system, which is characterized in that the isomery security system includes the first security protection
System and the second security system, first security system is equipped with the list library of deploying to ensure effective monitoring and control of illegal activities for storing multiple first facial images, described
Second security system acquire the second facial image, the collaboration supervision method comprising steps of
By identical human face recognition model, the First Eigenvalue of the first facial image and the second feature of the second facial image are extracted
Value；
Similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue, obtains the similarity of the two；
If similarity is higher than preset value, it is believed that corresponding the first facial image and the second facial image is same people.
2. collaboration supervision method according to claim 1, which is characterized in that the collaboration supervision method further comprises the steps of:
After extracting the Second Eigenvalue of the First Eigenvalue and the second facial image of the first facial image, by the First Eigenvalue and
Second Eigenvalue is transmitted to a processing module；
Similarity comparison calculating is carried out to the First Eigenvalue and Second Eigenvalue in the processing module.
3. collaboration supervision method according to claim 2, which is characterized in that the collaboration supervision method further comprises the steps of:
If similarity is higher than preset value, warning information of deploying to ensure effective monitoring and control of illegal activities is generated；
The processing module warning information that will deploy to ensure effective monitoring and control of illegal activities is transmitted to the first security system.
4. collaboration supervision method according to claim 2, which is characterized in that taken in the second security system setting edge calculations
Business device is used to carry out the First Eigenvalue and Second Eigenvalue the processing of similarity comparison calculating in edge calculations server disposition
Module.
5. collaboration supervision method according to claim 4, which is characterized in that first security system passes through encrypted tunnel
The First Eigenvalue is transmitted to processing module.
6. collaboration supervision method according to claim 5, which is characterized in that the encrypted tunnel uses RSA Algorithm.
7. collaboration supervision method according to claim 2, which is characterized in that taken in the first security system setting edge calculations
Business device is used to carry out the First Eigenvalue and Second Eigenvalue the processing of similarity comparison calculating in edge calculations server disposition
Module.
8. collaboration supervision method according to claim 1, which is characterized in that regularly update the name of deploying to ensure effective monitoring and control of illegal activities of the first security system
Dan Ku.
9. collaboration supervision method according to claim 8, which is characterized in that it is described deploy to ensure effective monitoring and control of illegal activities list library include personnel's name,
The information such as the first facial image, age, gender.
10. -9 any collaboration supervision method according to claim 1, which is characterized in that first security system it is close
Grade is higher than the second security system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910502389.2A CN110414315A (en) | 2019-06-11 | 2019-06-11 | A kind of collaboration supervision method of isomery security system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910502389.2A CN110414315A (en) | 2019-06-11 | 2019-06-11 | A kind of collaboration supervision method of isomery security system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110414315A true CN110414315A (en) | 2019-11-05 |
Family
ID=68358978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910502389.2A Pending CN110414315A (en) | 2019-06-11 | 2019-06-11 | A kind of collaboration supervision method of isomery security system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110414315A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
| CN206164722U (en) * | 2016-09-21 | 2017-05-10 | 深圳市泛海三江科技发展有限公司 | Discuss super electronic monitoring system based on face identification |
| CN106709468A (en) * | 2016-12-31 | 2017-05-24 | 北京中科天云科技有限公司 | City region surveillance system and device |
| CN107644204A (en) * | 2017-09-12 | 2018-01-30 | 南京凌深信息科技有限公司 | A kind of human bioequivalence and tracking for safety-protection system |
| CN109191635A (en) * | 2018-08-21 | 2019-01-11 | 万翼科技有限公司 | Objective method, apparatus and storage medium are sentenced based on face recognition technology |
| CN109859426A (en) * | 2019-01-24 | 2019-06-07 | 广州市炬盾科技发展有限公司 | A kind of community security protection management system |
-
2019
- 2019-06-11 CN CN201910502389.2A patent/CN110414315A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
| CN206164722U (en) * | 2016-09-21 | 2017-05-10 | 深圳市泛海三江科技发展有限公司 | Discuss super electronic monitoring system based on face identification |
| CN106709468A (en) * | 2016-12-31 | 2017-05-24 | 北京中科天云科技有限公司 | City region surveillance system and device |
| CN107644204A (en) * | 2017-09-12 | 2018-01-30 | 南京凌深信息科技有限公司 | A kind of human bioequivalence and tracking for safety-protection system |
| CN109191635A (en) * | 2018-08-21 | 2019-01-11 | 万翼科技有限公司 | Objective method, apparatus and storage medium are sentenced based on face recognition technology |
| CN109859426A (en) * | 2019-01-24 | 2019-06-07 | 广州市炬盾科技发展有限公司 | A kind of community security protection management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458154B (en) | Face recognition method, face recognition device and computer-readable storage medium | |
| CN107147652B (en) | A kind of safety fusion authentication method of the polymorphic identity of user based on block chain | |
| US20230116801A1 (en) | Image authenticity detection method and device, computer device, and storage medium | |
| CN107566781B (en) | Video monitoring method and video monitoring equipment | |
| CN108446680A (en) | A kind of method for secret protection in face authentication system based on edge calculations | |
| CN111428559A (en) | Method and device for detecting wearing condition of mask, electronic equipment and storage medium | |
| CN104823203A (en) | Biometric template security and key generation | |
| CN105635099A (en) | Identity authentication method, identity authentication system, terminal and server | |
| CN111882233A (en) | Storage risk early warning method, system and device based on block chain and storage medium | |
| CN110399225A (en) | Monitoring information processing method, system and computer system | |
| US11023714B2 (en) | Suspiciousness degree estimation model generation device | |
| CN108932774A (en) | information detecting method and device | |
| CN109344709A (en) | A kind of face generates the detection method of forgery image | |
| CN111583485A (en) | Community access control system, access control method and device, access control unit and medium | |
| CN112381000A (en) | Face recognition method, device, equipment and storage medium based on federal learning | |
| CN110414315A (en) | A kind of collaboration supervision method of isomery security system | |
| CN110222187B (en) | Common activity detection and data sharing method for protecting user privacy | |
| CN102413148B (en) | Biological characteristic remote authentication method based on visual codes | |
| CN113762970A (en) | Data processing method and device, computer readable storage medium and computer equipment | |
| CN112288088B (en) | Business model training method, device and system | |
| TWI709921B (en) | A system and method for object recognition | |
| CN114157473A (en) | Biometric technology sharing and verification method, system, device and medium | |
| CN209821849U (en) | Owl face recognition early warning system | |
| Vulfin et al. | Cognitive security modeling of biometric system of neural network cryptography | |
| Patil et al. | Enhancement of feature extraction in image quality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |